Please use this identifier to cite or link to this item:
Title: Reliability estimation using Markov chain Monte carlo-based tail modeling
Authors: Bayrak, Gamze
 Acar, Erdem
Keywords: Reliability analysis
Time-dependent reliability
Issue Date: Mar-2018
Publisher: American Institute of Aeronautics and Astronautics Inc.
Source: Bayrak, G., & Acar, E. (2017). Reliability Estimation Using Markov Chain Monte Carlo–Based Tail Modeling. AIAA Journal, 56(3), 1211-1224.
Abstract: Tail modeling is an efficient method used in reliability estimation of highly safe structures. Classical tail modeling is based on performing limit-state function evaluations through a sampling scheme, selecting a threshold value to specify the tail part of the cumulative distribution function, fitting a proper model to the tail part, and estimating the reliability. In this approach, limit-state function calculations that do not belong to the tail part are mostly discarded, and so majority of limit-state evaluations are wasted. In this paper, Markov chain Monte Carlo method with Metropolis–Hastings algorithm is used to draw samples from the tail part only so that a more accurate reliability index prediction is achieved. A commonly used proposal distribution formula is modified by using a scale parameter. The optimal value of this scale parameter is obtained for various numerical example problems with a varying number of random variables, and an approximate relationship is obtained between the optimal value of the scale parameter and the number of random variables. The approximate relationship is tested on the reliability prediction of a horizontal axis wind turbine and observed to work well. It is also found that the proposed approach is more accurate than the classical tail modeling when the number of variables is less than or equal to four. For a larger number of random variables, none of the two approaches are found to be superior to another.
ISSN: 00011452
Appears in Collections:Makine Mühendisliği Bölümü / Department of Mechanical Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record

CORE Recommender


checked on Sep 23, 2022


checked on Sep 24, 2022

Page view(s)

checked on Dec 26, 2022

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.